Visual Studio Code Marketplace MCP server for AI agents

Let Claude, ChatGPT or your own agent read Visual Studio Code Marketplace: 2 typed functions through one MCP server. No Visual Studio Code Marketplace API key needed.

Functions
2
Sign-in
Not needed
Works with
MCP, HTTP, Node, Python

Connect

Just Visual Studio Code Marketplace

An MCP server for Visual Studio Code Marketplace alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.

https://api.bowmark.ai/mcp/site/marketplace_visualstudio
Every site

One MCP server for Visual Studio Code Marketplace and every other site Bowmark covers. Your agent looks up what it needs and calls it.

https://api.bowmark.ai/mcp
Set it up in your client

Both need a Bowmark API key. The quickstart gets you one and a first result in a few minutes.

Functions

Open a function to see its arguments, what it returns and how to call it.

Read 2
  • getExtensionStatsLooks up one VS Code extension by its "publisher.extension" id (the id shown in the extension's own URL and in code --list-extensions) and returns…

    Arguments

    NameTypeRequired
    extensionIdstringYes

    Returns marketplaceExtensionStats

    interface marketplaceExtensionStats {
      extensionId: string;
      displayName: string;
      publisherDisplayName: string;
      shortDescription: string;
      version: string;
      lastUpdated: string;
      installCount: number;
      averageRating: number | null;
      ratingCount: number;
    }

    HTTP endpoint

    POST https://api.bowmark.ai/v1/sites/marketplace_visualstudio/getExtensionStats

    Call it

    import { bowmark } from "@bowmark/web";
    
    const result = await bowmark.providers.marketplace_visualstudio.getExtensionStats("ms-python.python");
  • searchExtensionsFull-text searches the VS Code Marketplace for extensions matching a query, ordered by install count, so a caller no longer has to already hold a…

    Arguments

    NameTypeRequired
    querystringYes

    Returns marketplaceSearchResult[]

    interface marketplaceSearchResult {
      extensionId: string;
      displayName: string;
      publisherDisplayName: string;
      shortDescription: string;
      installCount: number;
      averageRating: number | null;
      ratingCount: number;
    }

    HTTP endpoint

    POST https://api.bowmark.ai/v1/sites/marketplace_visualstudio/searchExtensions

    Call it

    import { bowmark } from "@bowmark/web";
    
    const result = await bowmark.providers.marketplace_visualstudio.searchExtensions("python linting");

Use it from code